Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    locations or specific places

    oai_token-act-pair · gpt-3.5-turbo

    nouns that refer to structures or established entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coliseum
    -0.62
     Hots
    -0.61
     Aren
    -0.59
     peripher
    -0.58
     Sparkle
    -0.58
     gorge
    -0.57
     batter
    -0.57
     ______
    -0.57
     somet
    -0.56
     etc
    -0.56
    POSITIVE LOGITS
    aments
    1.04
    ings
    1.01
    ages
    0.99
    atories
    0.97
    stones
    0.96
    heading
    0.96
    aus
    0.95
    emark
    0.95
    points
    0.95
    piece
    0.94
    Act Density 0.412%

    No Known Activations